
import os
import glob
import numpy as np
import pandas as pd
import seaborn as sns
from matplotlib import rc
import matplotlib.pyplot as plt
import plotly.express as px
import plotly.graph_objects as go
from sklearn.linear_model import LinearRegression
from IPython.display import display
from src import data_processing as dp
from src import sanky_chart as sc
from src import match_length as ml
from src import serving_analysis as sa
from src import mental_toughness as mt
from src import rising_star as rs


all_data = dp.read_gslam_files("data/atp_matches*.csv")
all_data.head()


data_other = dp.remove_player(["Roger Federer", "Rafael Nadal", "Novak Djokovic"], all_data, 'winner')
sum_other = data_other.sum()
data_other.head()


data_federer = all_data[all_data['winner_name'] == "Roger Federer"].copy()
data_federer.drop([ 'winner_name' ], axis=1, inplace=True)
data_federer.head()


data_nadal = all_data[all_data['winner_name'] == "Rafael Nadal"].copy()
data_nadal.drop([ 'winner_name' ], axis=1, inplace=True)
data_nadal.head()


data_djoker = all_data[all_data['winner_name'] == "Novak Djokovic"].copy()
data_djoker.drop([ 'winner_name' ], axis=1, inplace=True)
data_djoker.head()


data_zverev = all_data[all_data['winner_name'] == "Alexander Zverev"].copy()
data_zverev.drop([ 'winner_name' ], axis=1, inplace=True)
data_zverev.head()


data_thiem = all_data[all_data['winner_name'] == "Dominic Thiem"].copy()
data_thiem.drop([ 'winner_name' ], axis=1, inplace=True)
data_thiem.head()


#data taken for Sankey diagram is for top 20 players, so that the visualization is clear
tgs = len(all_data) #total grand slam matches played
sanky_data = all_data.groupby('winner_name',as_index=False).size().sort_values('size', ascending=False).head(20) #data for sanky diagram
sanky_data


sanky_data['total_grand_slams'] = 'Grand slam matches from 2003 to 2020: ' + str(+ tgs)
sanky_data["winner_name"] = sanky_data["winner_name"] +": "+ (sanky_data['size']).astype(str)
sanky_data


data, layout = sc.sanky_chart_data(sanky_data)
fig = go.Figure(data=[data], layout=layout)
 
fig.show()


# Fetch winning and losing match length for Roger Federer
lose_federer, win_federer = ml.player_match_length("Roger Federer", data_other, data_federer)

# Fetch winning and losing match length for Rafael Nadal
lose_nadal, win_nadal = ml.player_match_length("Rafael Nadal", data_other, data_nadal)

# Fetch winning and losing match length for Novak Djokovic
lose_djoker, win_djoker = ml.player_match_length("Novak Djokovic", data_other, data_djoker)

# Fetch winning and losing match length for other players
win_other = data_other[data_other['minutes'] <= 400]
win_other.insert(0, column = "Result", value = ['Win']*len(win_other))
win_other.insert(0, column = "Name", value = ["Other"]*len(win_other))
lose_other = dp.remove_player(["Roger Federer", "Rafael Nadal", "Novak Djokovic"], all_data, 'loser')
lose_other = lose_other[lose_other['minutes'] <= 400]
lose_other.insert(0, column = "Result", value = ['Lose']*len(lose_other))
lose_other.insert(0, column = "Name", value = ["Other"]*len(lose_other))

violin_data = pd.concat([win_federer, lose_federer, win_nadal, lose_nadal, win_djoker, lose_djoker, win_other, lose_other])
violin_data = violin_data.rename(columns={"minutes": "Minutes"}, errors="raise")


sns.set(style="darkgrid")
sns.violinplot(x="Name", y="Minutes", hue="Result", data=violin_data, palette="Pastel1", split=True).set(title='Match Length of Big 3 and Other Players')
plt.show()


data_federer, sum_federer = sa.player_data("Roger Federer", all_data)
data_nadal, sum_nadal = sa.player_data("Rafael Nadal", all_data)
data_djoker, sum_djoker = sa.player_data("Novak Djokovic", all_data)

#rising star match length t Alexander Zverev Dominic Thiem 
data_zverev, sum_zverev = sa.player_data("Alexander Zverev", all_data)
data_thiem, sum_thiem = sa.player_data("Dominic Thiem", all_data)

# Counting number of ace point played by every winning player
ace_winner = sa.player_group_data(all_data, 'w_ace')
# Counting number of firstserve played by every winning player
firstserve_winner = sa.player_group_data(all_data, 'w_1stWon')
# Counting number of secondserve played by every winning player
secondserve_winner = sa.player_group_data(all_data, 'w_2ndWon')
# Counting number of double faults by every player
df_winner = all_data[['winner_name', 'w_df']].groupby('winner_name').sum()
df_winner = pd.DataFrame(df_winner)
df_winner.head()


# Data
r = [0,1,2,3]
ff, fs, fd = sa.serving_data(sum_federer)
nf, ns, nd = sa.serving_data(sum_nadal)
df, ds, dd = sa.serving_data(sum_djoker) 
of, os, od = sa.serving_data(sum_other) 
tf, ts, td = sa.serving_data(sum_thiem) 
zf, zs, zd = sa.serving_data(sum_zverev) 

score_Federer_serving = sa.score_serving(ff,fs,fd)
score_Nadal_serving = sa.score_serving(nf,ns,nd)
score_Djoker_serving = sa.score_serving(df,ds,dd)
score_Other_serving = sa.score_serving(of,os,od)
score_Zverev_serving = sa.score_serving(zf,zs,zd)
score_Thiem_serving = sa.score_serving(tf,ts,td)
print(score_Zverev_serving, score_Thiem_serving)

raw_data = {'greenBars': [ff, nf, df, of], 'orangeBars': [fs, ns, ds,os], 'blueBars': [fd, nd, dd, od]}
df = pd.DataFrame(raw_data)
 
# From raw value to percentage
totals = [i+j+k for i,j,k in zip(df['greenBars'], df['orangeBars'], df['blueBars'])]
greenBars = [i / j * 100 for i,j in zip(df['greenBars'], totals)]
orangeBars = [i / j * 100 for i,j in zip(df['orangeBars'], totals)]
blueBars = [i / j * 100 for i,j in zip(df['blueBars'], totals)]
# plot
barWidth = 0.85
names = ('Federer','Nadal','Djokovic','Others')
# Create green Bars
plt.bar(r, greenBars, color='#b5ffb9', edgecolor='white', width=barWidth, label="First serve win")
# Create orange Bars
plt.bar(r, orangeBars, bottom=greenBars, color='#f9bc86', edgecolor='white', width=barWidth, label="Second serve win")
# Create blue Bars
plt.bar(r, blueBars, bottom=[i+j for i,j in zip(greenBars, orangeBars)], color='#a3acff', edgecolor='white', width=barWidth, label="Double fault")

# Custom x axis
plt.xticks(r, names)
plt.xlabel("Name")
plt.ylabel("Percent of all serves")
plt.title("Serve proportion")
# Add a legend
plt.legend(loc='upper left', bbox_to_anchor=(1,1), ncol=1)
 
# Show graphic
plt.show()

74.35768623510836 76.99489387264717


fig, axis = plt.subplots(figsize=(15,10))
# Grid lines, Xticks, Xlabel, Ylabel

axis.yaxis.grid(True)
axis.xaxis.grid(True)
axis.set_title('Correlation between ace and double fault',fontsize=25, pad=25.0)
axis.set_xlabel('Double faults per Serve Point(%)',fontsize=20, labelpad= 25.0)
axis.set_ylabel('Aces per Serve Point(%)',fontsize=20, labelpad=25.0)

ace_data = (ace_winner['w_ace']).values.reshape(-1, 1)
df_data = (df_winner['w_df']).values.reshape(-1, 1)
firstserve_win = firstserve_winner['w_1stWon'].values.reshape(-1, 1)
secondserve_win = secondserve_winner['w_2ndWon'].values.reshape(-1, 1)
X = df_data/(firstserve_win+secondserve_win+df_data)*100
Y = ace_data/(firstserve_win+secondserve_win+df_data)*100

linear_regressor_one = LinearRegression()  # create object for the class
linear_regressor_one.fit(X, Y)  # perform linear regression
Y_pred = linear_regressor_one.predict(X)  # make predictions


plt.plot(X, Y_pred, color='red')
plt.xticks(fontsize=15)
plt.yticks(fontsize=15)

axis.scatter(X, Y)
plt.scatter (*sa.serve_percentage(sum_federer), s=200, marker = 's', color='r', label = 'Roger Federer')
plt.scatter (*sa.serve_percentage(sum_nadal), s=200, marker = 's', color='g', label = 'Novak Djokovic')
plt.scatter (*sa.serve_percentage(sum_djoker), s=200, marker = 's', color='y', label = 'Rafael Nadal')
plt.legend(prop={'size': 20})

<matplotlib.legend.Legend at 0x7fa74450a130>


# Group the data by winner name and add all the break points
mental_df = all_data[['winner_name', 'w_bpSaved', 'w_bpFaced']].groupby('winner_name').sum()

# Add a percentage collumn with the breakpoint percentage
mental_df['percentage'] = mental_df.apply(lambda x: mt.get_percentage(x['w_bpSaved'], x['w_bpFaced']), axis=1)

# Add a mental points collumn with the mental point scores
mt.add_mental_points_col(mental_df, list(mental_df.index), all_data)

# Plot the scatterplot
fig, ax = plt.subplots(figsize=(8,6))
ax.scatter(mental_df['mental_score'], mental_df['percentage'], s=20)
ax.set_title("Break Point Win Percentage vs. Mental Point Score")
ax.set_xlabel('Mental Point Score')
ax.set_ylabel('Break Point Win Percentage')
mt.annotate_plot(ax, mental_df, ["Roger Federer", "Novak Djokovic", "Rafael Nadal"], ["r", "g", "y"])

# plt.scatter (2.57,15.253, s=200, marker = 's', color='r', label = 'Federer')
# plt.scatter (2.94, 6.6634, s=200, marker = 's', color='g', label = 'Nadal')
# plt.scatter (3.6525, 10.563, s=200, marker = 's', color='y', label = 'Djokovic')
plt.legend(prop={'size': 15})

plt.show()

mental_df = mental_df.sort_values('mental_score',ascending=False)


pd.set_option('display.max_rows',525)
mental_df.head(30)


# Calculate the difference of losing and winning match length for different players
dif_Federer = rs.match_len_diff(lose_federer, win_federer)
dif_Nadal = rs.match_len_diff(lose_nadal, win_nadal)
dif_Djoker = rs.match_len_diff(lose_djoker, win_djoker)
dif_Other = rs.match_len_diff(lose_other, win_other)

print(dif_Federer,dif_Nadal,dif_Djoker,dif_Other)
group_win = all_data.groupby(['winner_name'])
group_lose = all_data.groupby(['loser_name'])
dif = []
for name in group_win.groups.keys():
    player_win = group_win.get_group(name)
    win_length = player_win['minutes'].mean()
    player_lose = group_lose.get_group(name)
    lose_length = player_lose['minutes'].mean()
    dif.append(lose_length - win_length)

dif.sort(reverse = True)
dif_Largest = max(dif)
dif_Least = min(dif)

# Calculate the scores of match length for different players
score_Federer_length = rs.match_length_score(dif_Federer, dif_Least, dif_Largest)
score_Nadal_length = rs.match_length_score(dif_Nadal, dif_Least, dif_Largest)
score_Djoker_length = rs.match_length_score(dif_Djoker, dif_Least, dif_Largest)
score_Other_length = rs.match_length_score(dif_Other, dif_Least, dif_Largest)

59.29629629629629 30.856630824372758 29.57163671685285 -1.7450049915708803


score_Federer_mental = mental_df.loc['Roger Federer','mental_score']
score_Djoker_mental = mental_df.loc['Novak Djokovic','mental_score']
score_Nadal_mental = mental_df.loc['Rafael Nadal','mental_score']
score_Zverev_mental = mental_df.loc['Alexander Zverev','mental_score']
score_Thiem_mental = mental_df.loc['Dominic Thiem','mental_score']
mental_df_other = mental_df.drop(['Roger Federer','Novak Djokovic','Rafael Nadal'])
score_Other_mental = mental_df_other['mental_score'].mean()


categories = ['Serving Skills','Match Length','Mental Toughness','Serving Skills']

fig = go.Figure()

fig.add_trace(go.Scatterpolar(
      r=[score_Other_serving, score_Other_length,score_Other_mental,score_Other_serving],
      theta=categories,
      fill=None,
      name='Other player average'
))

fig.update_layout(

        title=dict(
        text="Other player average",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),
  polar=dict(
    radialaxis=dict(
      visible=True,
      range=[0, 100]
    )),
  showlegend=True
)

fig.show()


categories = ['Serving Skills','Match Length','Mental Toughness','Serving Skills']

fig = go.Figure()

fig.add_trace(go.Scatterpolar(
      r=[score_Federer_serving, score_Federer_length,score_Federer_mental,score_Federer_serving],
      theta=categories,
      fill=None,
      name='Federer'
))

fig.add_trace(go.Scatterpolar(
      r=[score_Djoker_serving, score_Djoker_length,score_Djoker_mental,score_Djoker_serving],
      theta=categories,
      fill=None,
      name='Djokovic'
))
fig.add_trace(go.Scatterpolar(
      r=[score_Nadal_serving, score_Nadal_length,score_Nadal_mental,score_Nadal_serving],
      theta=categories,
      fill=None,
      name='Nadal'
))
fig.update_layout(
            title=dict(
        text="Big 3",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),
  polar=dict(
    radialaxis=dict(
      visible=True,
      range=[50, 100]
    )),
  showlegend=True
)

fig.show()


average_Big3_serving = (score_Federer_serving + score_Nadal_serving + score_Djoker_serving)/3
average_Big3_length = (score_Federer_length + score_Nadal_length + score_Djoker_length)/3
average_Big3_mental = (score_Federer_mental + score_Nadal_mental + score_Djoker_mental)/3


categories = ['Serving Skills','Match Length','Mental Toughness','Serving Skills']

fig = go.Figure()

fig.add_trace(go.Scatterpolar(
      r=[average_Big3_serving, average_Big3_length,average_Big3_mental,average_Big3_serving],
      theta=categories,
      fill=None,
      name='Big 3 average'
))

fig.add_trace(go.Scatterpolar(
      r=[score_Other_serving, score_Other_length,score_Other_mental,score_Other_serving],
      theta=categories,
      fill=None,
      name='Other player average'
))
fig.update_layout(
        title=dict(
        text="Big 3 average VS Other player average",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),
    
  polar=dict(
    radialaxis=dict(
      visible=True,
      range=[0, 100]
    )),
  showlegend=True
)

fig.show()


#rising start Alexander Zverev Dominic Thiem


#rising star match length  Alexander Zverev Dominic Thiem 
lose_zverev, win_zverev = ml.player_match_length("Alexander Zverev", data_other, data_zverev)
lose_thiem, win_thiem = ml.player_match_length("Dominic Thiem", data_other, data_thiem)

dif_Zverev = rs.match_len_diff(lose_zverev, win_zverev)
dif_Thiem = rs.match_len_diff(lose_thiem, win_thiem)

score_Zverev_length = rs.match_length_score(dif_Zverev, dif_Least, dif_Largest)
score_Thiem_length = rs.match_length_score(dif_Thiem, dif_Least, dif_Largest)

print(score_Zverev_length, score_Thiem_length)

70.6643932935493 67.38765071245889


categories = ['Serving Skills','Match Length','Mental Toughness','Serving Skills']

fig = go.Figure()

fig.add_trace(go.Scatterpolar(
      r=[average_Big3_serving, average_Big3_length,average_Big3_mental,average_Big3_serving],
      theta=categories,
      fill=None,
      name='Big 3 average'
))

fig.add_trace(go.Scatterpolar(
      r=[score_Zverev_serving, score_Zverev_length,score_Zverev_mental,score_Zverev_serving],
      theta=categories,
      fill=None,
      name='Zverev'
))
fig.add_trace(go.Scatterpolar(
      r=[score_Thiem_serving, score_Thiem_length,score_Thiem_mental,score_Thiem_serving],
      theta=categories,
      fill=None,
      name='Thiem'
))
fig.add_trace(go.Scatterpolar(
      r=[score_Other_serving, score_Other_length,score_Other_mental,score_Other_serving],
      theta=categories,
      fill=None,
      name='Other player average',
      marker={'color':'#FFA15A'}
))
fig.update_layout(
    title=dict(
        text="Big 3 average VS Rising Star VS Other player average",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),
    
  polar=dict(
    radialaxis=dict(
      visible=True,
      range=[0, 85]
    )),
  showlegend=True
)

fig.show()


categories = ['Serving Skills','Match Length','Mental Toughness','Serving Skills']

fig = go.Figure()

fig.add_trace(go.Scatterpolar(
      r=[score_Federer_serving, score_Federer_length,score_Federer_mental,score_Federer_serving],
      theta=categories,
      fill=None,
      name='Federer'
))

fig.add_trace(go.Scatterpolar(
      r=[score_Djoker_serving, score_Djoker_length,score_Djoker_mental,score_Djoker_serving],
      theta=categories,
      fill=None,
      name='Djokovic'
      
))
fig.add_trace(go.Scatterpolar(
      r=[score_Nadal_serving, score_Nadal_length,score_Nadal_mental,score_Nadal_serving],
      theta=categories,
      fill=None,
      name='Nadal'
))

fig.add_trace(go.Scatterpolar(
      r=[score_Zverev_serving, score_Zverev_length,score_Zverev_mental,score_Zverev_serving],
      theta=categories,
      fill=None,
      name='Zverev',
      marker={'color':'#7F7F7F'}
))
fig.add_trace(go.Scatterpolar(
      r=[score_Thiem_serving, score_Thiem_length,score_Thiem_mental,score_Thiem_serving],
      theta=categories,
      fill=None,
      name='Thiem'
))

fig.update_layout(
        title=dict(
        text="Big 3 VS Rising Star",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),
  
  polar=dict(
    radialaxis=dict(
      visible=True,
      range=[0,100]
    )),
  showlegend=True
)

fig.show()


ranking_data = dp.read_ranking_files("data/atp_rankings*.csv")
ranking_data


#100644 Alexander Zverev
#106233 Dominic Thiem
#103819 Federer
#104745 Nadal
#104925 Djokovic
ranking = ranking_data[(ranking_data['player'].isin([100644,106233,103819,104745,104925]))]
ranking = ranking.sort_values(by=['ranking_date'])
ranking['ranking_date'] = pd.to_datetime(ranking['ranking_date'], format='%Y%m%d')
ranking = ranking.replace(100644,'Zverev')
ranking = ranking.replace(106233,'Thiem')
ranking = ranking.replace(103819,'Federer')
ranking = ranking.replace(104745,'Nadal')
ranking = ranking.replace(104925,'Djokovic')
ranking


fig = px.line(ranking, x="ranking_date", y="rank", color="player")
 
fig.update_yaxes(autorange="reversed")
fig.update_layout(
    title=dict(
        text="Big 3 VS Rising Star Ranking",
        y=0.95,
        x=0.5,
        xanchor= 'center',
        yanchor= 'top',
        font=dict(size=20)
    ),

)
fig.show()

	tourney_name	surface	tourney_level	winner_name	loser_name	score	best_of	round	minutes	w_ace	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
0	Roland Garros	Clay	G	Rafael Nadal	Marcos Daniel	7-5 6-4 6-3	5	R128	143.0	3.0	...	4.0	7.0	4.0	1.0	93.0	52.0	32.0	17.0	4.0	11.0
1	Roland Garros	Clay	G	Teymuraz Gabashvili	Igor Kunitsyn	6-7(6) 7-6(5) 6-3 6-1	5	R128	191.0	12.0	...	3.0	7.0	3.0	1.0	129.0	86.0	47.0	23.0	4.0	12.0
2	Roland Garros	Clay	G	Andrey Golubev	Denis Gremelmayr	6-3 6-3 6-2	5	R128	98.0	7.0	...	2.0	3.0	4.0	3.0	83.0	54.0	32.0	10.0	1.0	7.0
3	Roland Garros	Clay	G	Lleyton Hewitt	Ivo Karlovic	6-7(1) 6-7(4) 7-6(4) 6-4 6-3	5	R128	236.0	19.0	...	5.0	6.0	55.0	4.0	169.0	124.0	102.0	20.0	4.0	8.0
4	Roland Garros	Clay	G	Robin Soderling	Kevin Kim	7-6(4) 7-6(4) 6-2	5	R128	137.0	11.0	...	3.0	7.0	10.0	3.0	112.0	56.0	40.0	23.0	7.0	13.0

	tourney_name	surface	tourney_level	winner_name	loser_name	score	best_of	round	minutes	w_ace	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
1	Roland Garros	Clay	G	Teymuraz Gabashvili	Igor Kunitsyn	6-7(6) 7-6(5) 6-3 6-1	5	R128	191.0	12.0	...	3.0	7.0	3.0	1.0	129.0	86.0	47.0	23.0	4.0	12.0
2	Roland Garros	Clay	G	Andrey Golubev	Denis Gremelmayr	6-3 6-3 6-2	5	R128	98.0	7.0	...	2.0	3.0	4.0	3.0	83.0	54.0	32.0	10.0	1.0	7.0
3	Roland Garros	Clay	G	Lleyton Hewitt	Ivo Karlovic	6-7(1) 6-7(4) 7-6(4) 6-4 6-3	5	R128	236.0	19.0	...	5.0	6.0	55.0	4.0	169.0	124.0	102.0	20.0	4.0	8.0
4	Roland Garros	Clay	G	Robin Soderling	Kevin Kim	7-6(4) 7-6(4) 6-2	5	R128	137.0	11.0	...	3.0	7.0	10.0	3.0	112.0	56.0	40.0	23.0	7.0	13.0
5	Roland Garros	Clay	G	Denis Istomin	Santiago Giraldo	6-3 6-7(2) 6-3 7-6(4)	5	R128	205.0	21.0	...	1.0	3.0	5.0	2.0	158.0	86.0	60.0	40.0	11.0	15.0

	tourney_name	surface	tourney_level	loser_name	score	best_of	round	minutes	w_ace	w_df	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
63	Roland Garros	Clay	G	Alberto Martin	6-4 6-3 6-2	5	R128	103.0	10.0	0.0	...	0.0	1.0	0.0	3.0	87.0	56.0	34.0	13.0	5.0	10.0
95	Roland Garros	Clay	G	Jose Acasuso	7-6(8) 5-7 7-6(2) 6-2	5	R64	205.0	11.0	0.0	...	5.0	10.0	5.0	2.0	154.0	96.0	59.0	31.0	6.0	12.0
111	Roland Garros	Clay	G	Paul Henri Mathieu	4-6 6-1 6-4 6-4	5	R32	166.0	14.0	3.0	...	5.0	7.0	8.0	3.0	126.0	75.0	49.0	24.0	11.0	16.0
119	Roland Garros	Clay	G	Tommy Haas	6-7(4) 5-7 6-4 6-0 6-2	5	R16	187.0	16.0	1.0	...	3.0	5.0	11.0	3.0	145.0	93.0	63.0	28.0	8.0	15.0
123	Roland Garros	Clay	G	Gael Monfils	7-6(6) 6-2 6-4	5	QF	130.0	8.0	1.0	...	4.0	4.0	7.0	1.0	105.0	61.0	41.0	22.0	2.0	5.0

	tourney_name	surface	tourney_level	loser_name	score	best_of	round	minutes	w_ace	w_df	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
0	Roland Garros	Clay	G	Marcos Daniel	7-5 6-4 6-3	5	R128	143.0	3.0	0.0	...	4.0	7.0	4.0	1.0	93.0	52.0	32.0	17.0	4.0	11.0
64	Roland Garros	Clay	G	Teymuraz Gabashvili	6-1 6-4 6-2	5	R64	137.0	2.0	1.0	...	4.0	4.0	2.0	3.0	85.0	52.0	34.0	12.0	8.0	13.0
96	Roland Garros	Clay	G	Lleyton Hewitt	6-1 6-3 6-1	5	R32	111.0	7.0	0.0	...	2.0	3.0	2.0	2.0	75.0	46.0	26.0	9.0	6.0	13.0
301	US Open	Hard	G	Richard Gasquet	6-2 6-2 6-3	5	R128	101.0	7.0	0.0	...	0.0	0.0	4.0	4.0	75.0	49.0	29.0	12.0	5.0	10.0
341	US Open	Hard	G	Nicolas Kiefer	6-0 3-6 6-3 6-4	5	R64	179.0	3.0	1.0	...	1.0	3.0	7.0	5.0	133.0	54.0	38.0	33.0	9.0	15.0

	tourney_name	surface	tourney_level	loser_name	score	best_of	round	minutes	w_ace	w_df	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
47	Roland Garros	Clay	G	Nicolas Lapentti	6-3 3-1 RET	5	R128	78.0	1.0	0.0	...	0.0	0.0	0.0	1.0	58.0	38.0	23.0	8.0	5.0	7.0
87	Roland Garros	Clay	G	Sergiy Stakhovsky	6-3 6-4 6-1	5	R64	124.0	5.0	2.0	...	3.0	5.0	6.0	3.0	107.0	62.0	38.0	16.0	11.0	18.0
174	Wimbledon	Grass	G	Julien Benneteau	6-7(8) 7-6(1) 6-2 6-4	5	R128	209.0	14.0	4.0	...	3.0	4.0	3.0	4.0	152.0	104.0	71.0	24.0	8.0	12.0
214	Wimbledon	Grass	G	Simon Greul	7-5 6-1 6-4	5	R64	120.0	13.0	6.0	...	6.0	10.0	0.0	2.0	87.0	53.0	26.0	16.0	7.0	15.0
234	Wimbledon	Grass	G	Mardy Fish	6-4 6-4 6-4	5	R32	119.0	8.0	1.0	...	0.0	1.0	6.0	1.0	96.0	56.0	42.0	16.0	8.0	12.0

Import Data from CSV¶

Data Cleaning¶

Organize other player data¶

Organize Federer data¶

Organize Nadal Data¶

Organize Djokovic data¶

Organize rising star data Alexander Zverev Dominic Thiem Nick Kyrgois¶

Sankey Data Creation by Considering Top 20 Tennis Players¶

Sankey data creation by considering top 20 tennis players¶

¶

Match Length Violin Plot¶

Serving Analysis¶

Percentage barplot¶

Scatter plot¶

Mental Toughness¶

Rising Star¶

Data process with match length¶

Data process with Mental toughness¶

Radar charts¶

Ranking of rising stars¶

	tourney_name	surface	tourney_level	loser_name	score	best_of	round	minutes	w_ace	w_df	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
1164	Roland Garros	Clay	G	Pierre Hugues Herbert	5-7 6-2 7-6(6) 7-5	5	R128	188.0	8.0	6.0	...	5.0	7.0	7.0	5.0	148.0	76.0	57.0	35.0	8.0	12.0
1217	Roland Garros	Clay	G	Stephane Robert	6-1 3-6 6-1 6-4	5	R64	129.0	5.0	2.0	...	5.0	8.0	11.0	7.0	100.0	48.0	35.0	20.0	5.0	12.0
1306	Wimbledon	Grass	G	Paul Henri Mathieu	6-3 6-4 6-2	5	R128	96.0	20.0	2.0	...	5.0	7.0	3.0	8.0	86.0	48.0	26.0	19.0	3.0	9.0
1352	Wimbledon	Grass	G	Mikhail Youzhny	6-4 3-6 6-0 4-6 6-2	5	R64	198.0	10.0	10.0	...	7.0	11.0	3.0	2.0	137.0	90.0	55.0	22.0	4.0	12.0
1441	US Open	Hard	G	Daniel Brands	3-6 6-1 6-4 7-6(4)	5	R128	155.0	4.0	7.0	...	2.0	4.0	7.0	9.0	126.0	70.0	49.0	27.0	8.0	12.0

	tourney_name	surface	tourney_level	loser_name	score	best_of	round	minutes	w_ace	w_df	...	w_bpSaved	w_bpFaced	l_ace	l_df	l_svpt	l_1stIn	l_1stWon	l_2ndWon	l_bpSaved	l_bpFaced
1036	Australian Open	Hard	G	Leonardo Mayer	6-2 7-6 4-6 7-6	5	R128	186.0	7.0	4.0	...	3.0	6.0	8.0	5.0	139.0	91.0	61.0	24.0	5.0	9.0
1090	Australian Open	Hard	G	Nicolas Almagro	6-3 6-1 6-3	5	R64	101.0	5.0	1.0	...	0.0	0.0	13.0	4.0	100.0	56.0	33.0	19.0	11.0	17.0
1166	Roland Garros	Clay	G	Inigo Cervantes Huegun	3-6 6-2 7-5 6-1	5	R128	158.0	5.0	1.0	...	6.0	9.0	6.0	4.0	118.0	69.0	44.0	19.0	10.0	17.0
1218	Roland Garros	Clay	G	Guillermo Garcia Lopez	7-5 6-4 7-6(3)	5	R64	145.0	7.0	7.0	...	6.0	9.0	5.0	4.0	112.0	52.0	37.0	28.0	7.0	12.0
1244	Roland Garros	Clay	G	Alexander Zverev	6-7(4) 6-3 6-3 6-3	5	R32	169.0	6.0	2.0	...	7.0	8.0	6.0	5.0	121.0	72.0	49.0	22.0	10.0	15.0

	winner_name	size
428	Roger Federer	324
377	Novak Djokovic	284
407	Rafael Nadal	279
50	Andy Murray	182
104	David Ferrer	143
495	Tomas Berdych	140
459	Stan Wawrinka	140
51	Andy Roddick	116
243	Jo-Wilfried Tsonga	115
317	Marin Cilic	115
151	Fernando Verdasco	110
164	Gael Monfils	108
288	Lleyton Hewitt	100
417	Richard Gasquet	98
257	Juan Martin del Potro	97
273	Kei Nishikori	95
499	Tommy Robredo	93
353	Mikhail Youzhny	88
147	Feliciano Lopez	86
354	Milos Raonic	84

	winner_name	size	total_grand_slams
428	Roger Federer: 324	324	Grand slam matches from 2003 to 2020: 8732
377	Novak Djokovic: 284	284	Grand slam matches from 2003 to 2020: 8732
407	Rafael Nadal: 279	279	Grand slam matches from 2003 to 2020: 8732
50	Andy Murray: 182	182	Grand slam matches from 2003 to 2020: 8732
104	David Ferrer: 143	143	Grand slam matches from 2003 to 2020: 8732
495	Tomas Berdych: 140	140	Grand slam matches from 2003 to 2020: 8732
459	Stan Wawrinka: 140	140	Grand slam matches from 2003 to 2020: 8732
51	Andy Roddick: 116	116	Grand slam matches from 2003 to 2020: 8732
243	Jo-Wilfried Tsonga: 115	115	Grand slam matches from 2003 to 2020: 8732
317	Marin Cilic: 115	115	Grand slam matches from 2003 to 2020: 8732
151	Fernando Verdasco: 110	110	Grand slam matches from 2003 to 2020: 8732
164	Gael Monfils: 108	108	Grand slam matches from 2003 to 2020: 8732
288	Lleyton Hewitt: 100	100	Grand slam matches from 2003 to 2020: 8732
417	Richard Gasquet: 98	98	Grand slam matches from 2003 to 2020: 8732
257	Juan Martin del Potro: 97	97	Grand slam matches from 2003 to 2020: 8732
273	Kei Nishikori: 95	95	Grand slam matches from 2003 to 2020: 8732
499	Tommy Robredo: 93	93	Grand slam matches from 2003 to 2020: 8732
353	Mikhail Youzhny: 88	88	Grand slam matches from 2003 to 2020: 8732
147	Feliciano Lopez: 86	86	Grand slam matches from 2003 to 2020: 8732
354	Milos Raonic: 84	84	Grand slam matches from 2003 to 2020: 8732

	w_df
winner_name
Adam Pavlasek	10.0
Adrian Mannarino	95.0
Adrian Menendez Maceiras	1.0
Adrian Ungur	6.0
Adrian Voinea	3.0

	w_bpSaved	w_bpFaced	percentage	mental_score
winner_name
Novak Djokovic	1046.0	1538.0	68.01	94
Roger Federer	972.0	1366.0	71.16	87
Stan Wawrinka	653.0	927.0	70.44	85
Marin Cilic	478.0	674.0	70.92	67
Andy Murray	746.0	1118.0	66.73	65
Feliciano Lopez	367.0	517.0	70.99	62
Rafael Nadal	1026.0	1444.0	71.05	60
John Isner	220.0	283.0	77.74	59
Gael Monfils	459.0	714.0	64.29	57
Fernando Verdasco	583.0	845.0	68.99	57
Kei Nishikori	442.0	688.0	64.24	57
Andreas Seppi	265.0	415.0	63.86	55
Janko Tipsarevic	256.0	380.0	67.37	50
Lleyton Hewitt	453.0	683.0	66.33	49
Nicolas Almagro	259.0	378.0	68.52	49
David Ferrer	589.0	920.0	64.02	48
Gilles Muller	219.0	283.0	77.39	46
Jo-Wilfried Tsonga	430.0	589.0	73.01	46
Tommy Robredo	441.0	653.0	67.53	46
Viktor Troicki	287.0	413.0	69.49	45
Gilles Simon	464.0	671.0	69.15	44
Jarkko Nieminen	336.0	498.0	67.47	43
Fabio Fognini	278.0	441.0	63.04	42
Tomas Berdych	528.0	709.0	74.47	40
Kevin Anderson	243.0	340.0	71.47	40
Tommy Haas	275.0	415.0	66.27	40
Philipp Kohlschreiber	323.0	426.0	75.82	37
Juan Carlos Ferrero	314.0	476.0	65.97	37
Andy Roddick	341.0	446.0	76.46	37
Mikhail Youzhny	457.0	668.0	68.41	36

	ranking_date	rank	player	points
0	20220103	1	104925	11540.0
1	20220103	2	106421	8640.0
2	20220103	3	100644	7840.0
3	20220103	4	126774	6540.0
4	20220103	5	126094	5150.0
...	...	...	...	...
915613	20191230	1922	134833	1.0
915614	20191230	1922	144856	1.0
915615	20191230	1922	202326	1.0
915616	20191230	1926	207307	1.0
915617	20191230	1927	208186	1.0

	ranking_date	rank	player	points
0	2010-01-04	1	Federer	10550.0
1	2010-01-04	2	Nadal	9205.0
2	2010-01-04	3	Djokovic	8310.0
1813	2010-01-11	2	Nadal	9310.0
1812	2010-01-11	1	Federer	10550.0
...	...	...	...	...
61916	2022-08-29	3	Nadal	5630.0
63848	2022-09-12	3	Nadal	5810.0
63850	2022-09-12	5	Zverev	5040.0
63852	2022-09-12	7	Djokovic	3570.0
65109	2022-09-12	216	Thiem	241.0